deprecate old models

smallcloudai · Feb 6, 2025 · 2edc99a · 2edc99a
1 parent cf2a13c
commit 2edc99a
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 2 deletions.
diff --git a/README.md b/README.md
@@ -116,8 +116,8 @@ Extensions > Refact.ai Assistant > Settings > Infurl
 | [deepseek-coder/5.7b/mqa-base](https://huggingface.co/deepseek-ai/deepseek-coder-5.7bmqa-base)          | +          |      | +           |                                                     |
 | [mixtral/8x7b/instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)               |            | +    |             |                                                     |
 | [deepseek-coder/33b/instruct](https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct)           |            | +    |             |                                                     |
-| [stable/3b/code](https://huggingface.co/stabilityai/stable-code-3b)                                     | +          |      |             |                                                     |
-| [llama3/8b/instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)                        | +          | +    |             |                                                     |
+| [stable/3b/code](https://huggingface.co/stabilityai/stable-code-3b)                                     | +          |      |             | +                                                   |
+| [llama3/8b/instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)                        | +          | +    |             | +                                                   |
 | [llama3.1/8b/instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)                    | +          | +    |             |                                                     |
 | [llama3.2/1b/instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)                         | +          | +    |             |                                                     |
 | [llama3.2/3b/instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)                         | +          | +    |             |                                                     |

diff --git a/refact_known_models/huggingface.py b/refact_known_models/huggingface.py
@@ -56,6 +56,7 @@
         },
         "required_memory_mb": 8000,
         "T": 4096,  # in fact this model allows 16k context, but we have 4k context at max in hf inference
+        "deprecated": True,
         "filter_caps": ["completion"],
     },
     "starcoder2/3b/base": {
@@ -93,6 +94,7 @@
         },
         "required_memory_mb": 20000,
         "T": 8192,
+        "deprecated": True,
         "filter_caps": ["completion", "chat"],
     },
     "llama3.1/8b/instruct": {